InnoLOG: 8th Thuringian AI Forum

Experts from the worlds of business, academia and public administration will present a varied programme featuring best-practice examples, specialist presentations, demonstrations and hands-on workshops – providing plenty of valuable inspiration for advancing AI within your own working environment. 

IMMS contribution – Workshop IV: ‘Sovereign AI on embedded systems’ 

Dr Tino Hutschenreuther and Sebastian Uziel  

The topic is control over one’s own data when using AI in industry: edge processing strengthens this control by processing data locally, close to where it is generated – not in the cloud. ‘Privacy by Design’ integrates data protection into hardware and software from the outset, ensuring that only generated information leaves the device. Challenges include energy consumption, limited storage and real-time requirements. The workshop will demonstrate solutions such as data reduction, compression and embedded AI to reduce the data stream on sensors and edge devices, thereby conserving resources.

IMMS demonstrator – Edge AI-based monitoring with “AWARE” (Advanced wireless AI-enabled real-time environment)

Wolfram Kattanek

This energy-efficient edge AI sensor system enables the development of various monitoring applications for industry. This solution enables AI algorithms to be utilised optimally on resource-constrained devices for IoT applications. This is achieved by performing as much data processing as possible close to the sensors and outsourcing as few tasks as possible to the network. The demonstrator provides a clear and interactive illustration of how a gearbox driven by an electric motor can be monitored for wear and defects using an intelligent sensor. During the demonstration, specific fault conditions can be deliberately induced. Sensor readings and the information extracted from them are displayed on a monitor.